This is original generated practice for the course effective Fall 2026, whose revised exam begins in May 2027. These are not official College Board questions. The preserved earlier practice test remains available as historical source material; this rehearsal uses the revised format and its own new task identities.
Allow 90 minutes for all 42 questions. Every question has four choices and one defensible answer. A graphing calculator with statistical capabilities is expected. Keep appropriate statistical formulas and tables available. Questions 12–14 share a probability setting, and questions 36–38 share a regression setting. The complete setting is repeated with each question so that a page position or screen reader does not hide needed information.
A deliberate first pass
Before calculating, identify what is being measured and what the question asks you to produce. A count of people with a yes/no response suggests a proportion; a measured time or distance suggests a quantitative mean. A paired design gives one set of within-unit differences, while two separately selected groups give independentsamples. The design determines the parameter and procedure before a calculator command does.
Read the subtraction order, conditioning event, and direction of a hypothesis carefully. In a conditional probability, the denominator is the group you are given. For a residual, use observed minus predicted. A difference defined as A minus B has a negative sign when A is lower. These small details can change an otherwise sensible calculation.
For an interval or test, separate the statistic from the parameter. A confidence interval estimates an unknown population value. A p-value describes how unusual the observed result would be under a specified null model. Neither attaches a probability to the hypothesis being true, and neither automatically supports a cause-and-effect conclusion. For a mean with unknown population standard deviation, the estimated standard error contains s/n rather than s/n.
When a graph or table is supplied, use its labels and units. Relative frequencies allow fair comparisons between differently sized groups. A residual pattern can reveal curvature even when the residuals average to zero. If a question asks about a simulated probability, count the qualifying simulation trials and divide by the total number of trials; do not silently replace the requested empirical estimate with a theoretical probability.
Using the 90 minutes
Forty-two questions in 90 minutes allow a little over two minutes per question on average. Make a first pass through questions you can resolve, record a choice, and revisit any that need a longer calculation. Check that a calculator output corresponds to the right model, parameter, degrees of freedom, and tail. Keep a few intermediate digits, then round to the precision of the choices. No rehearsal timer is enforced here, so set your own timer for a timed attempt.
Attempt the section before opening its separate worked answers. Afterward, use the explanations to identify whether a missed item came from model choice, a numerical step, a sign or unit, or the meaning of the result. Correct a reasoning error in words as well as changing a choice. The explanations are reviewed separately from the prompts; the answer page does not establish that a learning objective is mastered.
Original generated practice for the Fall 2026 course.
Glossary and deeper reading · 10 refreshers
These editorial refreshers supplement the reading. Definitions and examples are added guidance; original source wording and recorded answers remain in their original context.
Probability
Probability quantifies how likely an event is under a specified chance model. It lies between 0 and 1, with larger values representing greater likelihood. For example, drawing a red card from a well-shuffled standard deck has probability one half.
Statistical independence means that learning one outcome does not change the probability distribution of another. For two events, it implies that the probability of both occurring equals the product of their probabilities. For example, independent draws with replacement keep the second draw’s color probabilities unchanged by the first.
A sample is the subset of a population actually studied. How it is selected matters for the conclusions that can be drawn about the population. For example, 60 selected students may be a sample from a school’s full enrollment.
An event is a set of outcomes from a chance process’s sample space. The event occurs when the observed outcome belongs to that set. For example, rolling an even result is the event containing 2, 4, and 6 for a six-sided die.
Conditional probability measures the likelihood of one event when another event is known to have occurred. It restricts attention to the conditioning event, which must have positive probability. For example, knowing a drawn card is a face card changes the denominator when finding the probability it is a queen.
A statistic is a numerical summary calculated from sample data. Its value can change when a different sample is selected from the same population. For example, the proportion of walkers among 60 sampled students is a statistic.
A population parameter is a numerical feature of the population or probability model being studied. It is fixed for that defined population, although its value may be unknown. For example, the true proportion of all enrolled students who walk to school is a parameter.
Relative frequency is a group’s count divided by the total count. It can be written as a proportion or multiplied by 100 to give a percentage. For example, 8 choices out of 20 have relative frequency 0.4, or 40%.
A residual is an observed response minus its predicted response. A positive residual places the observed point above the fitted line, while a negative residual places it below. For example, an observed height of 18 centimeters and a predicted height of 16 centimeters give a residual of 2 centimeters.
Degrees of freedom describe the independent information remaining after constraints or estimated quantities are accounted for. The value depends on the procedure, rather than always being the sample size minus 1. For example, a one-sample t procedure uses n − 1 degrees of freedom, while simple regression inference uses n − 2.